Merge tag 'nfs-for-4.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Hightlights include:

  Stable bugfixes:
   - Fix mirror allocation in the writeback code to avoid a use after
     free
   - Fix the O_DSYNC writes to use the correct byte range
   - Fix 2 use after free issues in the I/O code

  Features:
   - Writeback fixes to split up the inode->i_lock in order to reduce
     contention
   - RPC client receive fixes to reduce the amount of time the
     xprt->transport_lock is held when receiving data from a socket into
     am XDR buffer.
   - Ditto fixes to reduce contention between call side users of the
     rdma rb_lock, and its use in rpcrdma_reply_handler.
   - Re-arrange rdma stats to reduce false cacheline sharing.
   - Various rdma cleanups and optimisations.
   - Refactor the NFSv4.1 exchange id code and clean up the code.
   - Const-ify all instances of struct rpc_xprt_ops

  Bugfixes:
   - Fix the NFSv2 'sec=' mount option.
   - NFSv4.1: don't use machine credentials for CLOSE when using
     'sec=sys'
   - Fix the NFSv3 GRANT callback when the port changes on the server.
   - Fix livelock issues with COMMIT
   - NFSv4: Use correct inode in _nfs4_opendata_to_nfs4_state() when
     doing and NFSv4.1 open by filehandle"

* tag 'nfs-for-4.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (69 commits)
  NFS: Count the bytes of skipped subrequests in nfs_lock_and_join_requests()
  NFS: Don't hold the group lock when calling nfs_release_request()
  NFS: Remove pnfs_generic_transfer_commit_list()
  NFS: nfs_lock_and_join_requests and nfs_scan_commit_list can deadlock
  NFS: Fix 2 use after free issues in the I/O code
  NFS: Sync the correct byte range during synchronous writes
  lockd: Delete an error message for a failed memory allocation in reclaimer()
  NFS: remove jiffies field from access cache
  NFS: flush data when locking a file to ensure cache coherence for mmap.
  SUNRPC: remove some dead code.
  NFS: don't expect errors from mempool_alloc().
  xprtrdma: Use xprt_pin_rqst in rpcrdma_reply_handler
  xprtrdma: Re-arrange struct rx_stats
  NFS: Fix NFSv2 security settings
  NFSv4.1: don't use machine credentials for CLOSE when using 'sec=sys'
  SUNRPC: ECONNREFUSED should cause a rebind.
  NFS: Remove unused parameter gfp_flags from nfs_pageio_init()
  NFSv4: Fix up mirror allocation
  SUNRPC: Add a separate spinlock to protect the RPC request receive list
  SUNRPC: Cleanup xs_tcp_read_common()
  ...

1 files changed, 9 insertions, 13 deletions

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index e4171f2abe37..11a1fbf7e59e 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -139,14 +139,11 @@ rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 static void
 rpcrdma_update_granted_credits(struct rpcrdma_rep *rep)
 {
-	struct rpcrdma_msg *rmsgp = rdmab_to_msg(rep->rr_rdmabuf);
 	struct rpcrdma_buffer *buffer = &rep->rr_rxprt->rx_buf;
+	__be32 *p = rep->rr_rdmabuf->rg_base;
 	u32 credits;
 
-	if (rep->rr_len < RPCRDMA_HDRLEN_ERR)
-		return;
-
-	credits = be32_to_cpu(rmsgp->rm_credit);
+	credits = be32_to_cpup(p + 2);
 	if (credits == 0)
 		credits = 1;	/* don't deadlock */
 	else if (credits > buffer->rb_max_requests)
@@ -173,21 +170,19 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 		goto out_fail;
 
 	/* status == SUCCESS means all fields in wc are trustworthy */
-	if (wc->opcode != IB_WC_RECV)
-		return;
-
 	dprintk("RPC:       %s: rep %p opcode 'recv', length %u: success\n",
 		__func__, rep, wc->byte_len);
 
-	rep->rr_len = wc->byte_len;
+	rpcrdma_set_xdrlen(&rep->rr_hdrbuf, wc->byte_len);
 	rep->rr_wc_flags = wc->wc_flags;
 	rep->rr_inv_rkey = wc->ex.invalidate_rkey;
 
 	ib_dma_sync_single_for_cpu(rdmab_device(rep->rr_rdmabuf),
 				   rdmab_addr(rep->rr_rdmabuf),
-				   rep->rr_len, DMA_FROM_DEVICE);
+				   wc->byte_len, DMA_FROM_DEVICE);
 
-	rpcrdma_update_granted_credits(rep);
+	if (wc->byte_len >= RPCRDMA_HDRLEN_ERR)
+		rpcrdma_update_granted_credits(rep);
 
 out_schedule:
 	queue_work(rpcrdma_receive_wq, &rep->rr_work);
@@ -198,7 +193,7 @@ out_fail:
 		pr_err("rpcrdma: Recv: %s (%u/0x%x)\n",
 		       ib_wc_status_msg(wc->status),
 		       wc->status, wc->vendor_err);
-	rep->rr_len = RPCRDMA_BAD_LEN;
+	rpcrdma_set_xdrlen(&rep->rr_hdrbuf, 0);
 	goto out_schedule;
 }
 
@@ -974,6 +969,8 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt)
 		rc = PTR_ERR(rep->rr_rdmabuf);
 		goto out_free;
 	}
+	xdr_buf_init(&rep->rr_hdrbuf, rep->rr_rdmabuf->rg_base,
+		     rdmab_length(rep->rr_rdmabuf));
 
 	rep->rr_cqe.done = rpcrdma_wc_receive;
 	rep->rr_rxprt = r_xprt;
@@ -1004,7 +1001,6 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 	spin_lock_init(&buf->rb_recovery_lock);
 	INIT_LIST_HEAD(&buf->rb_mws);
 	INIT_LIST_HEAD(&buf->rb_all);
-	INIT_LIST_HEAD(&buf->rb_pending);
 	INIT_LIST_HEAD(&buf->rb_stale_mrs);
 	INIT_DELAYED_WORK(&buf->rb_refresh_worker,
 			  rpcrdma_mr_refresh_worker);